Quantifying Analysis of Uncertainty in Medical Reporting: Creation of User and Context-Specific Uncertainty Profiles.

While uncertainty is ubiquitous in medical practice, minimal work to date has been performed to analyze the cause and effect relationship between uncertainty and patient outcomes. In medical imaging practice, uncertainty in the radiology report has been well documented to be a source of clinician dissatisfaction. Before one can effectively create intervention strategies aimed at reducing uncertainty, it must first be better understood through context- and user-specific analysis. One strategy for accomplishing this task is to characterize the source of uncertainty and create user-specific uncertainty profiles which take into account a number of provider-specific variables which may contribute to report uncertainty. The resulting data can in turn be used to create real-time report uncertainty metrics aimed at providing uncertainty analytics at the point of care, for the combined purposes of decision support, improved communication, and enhanced clinical/economic outcomes.

Quantitative Analysis of Uncertainty in Medical Reporting: Creating a Standardized and Objective Methodology.

Uncertainty in text-based medical reports has long been recognized as problematic, frequently resulting in misunderstanding and miscommunication. One strategy for addressing the negative clinical ramifications of report uncertainty would be the creation of a standardized methodology for characterizing and quantifying uncertainty language, which could provide both the report author and reader with context related to the perceived level of diagnostic confidence and accuracy. A number of computerized strategies could be employed in the creation of this analysis including string search, natural language processing and understanding, histogram analysis, topic modeling, and machine learning. The derived uncertainty data offers the potential to objectively analyze report uncertainty in real time and correlate with outcomes analysis for the purpose of context and user-specific decision support at the point of care, where intervention would have the greatest clinical impact.

Quantitative Analysis of Uncertainty in Medical Reporting: Part 3: Customizable Education, Decision Support, and Automated Alerts.

In order to better elucidate and understand the causative factors and clinical implications of uncertainty in medical reporting, one must first create a referenceable database which records a number of standardized metrics related to uncertainty language, clinical context, technology, and provider and patient data. The resulting analytics can in turn be used to create context and user-specific reporting guidelines, real-time decision support, educational resources, and quality assurance measures. If this technology can be directly integrated into reporting technology and workflow, the goal is to proactively improve clinical outcomes at the point of care.

Redefining the Practice of Peer Review Through Intelligent Automation-Part 3: Automated Report Analysis and Data Reconciliation.

One method for addressing existing peer review limitations is the assignment of peer review cases on a completely blinded basis, in which the peer reviewer would create an independent report which can then be cross-referenced with the primary reader report of record. By leveraging existing computerized data mining techniques, one could in theory automate and objectify the process of report data extraction, classification, and analysis, while reducing time and resource requirements intrinsic to manual peer review report analysis. Once inter-report analysis has been performed, resulting inter-report discrepancies can be presented to the radiologist of record for review, along with the option to directly communicate with the peer reviewer through an electronic data reconciliation tool aimed at collaboratively resolving inter-report discrepancies and improving report accuracy. All associated report and reconciled data could in turn be recorded in a referenceable peer review database, which provides opportunity for context and user-specific education and decision support.

Redefining the Practice of Peer Review Through Intelligent Automation Part 2: Data-Driven Peer Review Selection and Assignment.

In conventional radiology peer review practice, a small number of exams (routinely 5% of the total volume) is randomly selected, which may significantly underestimate the true error rate within a given radiology practice. An alternative and preferable approach would be to create a data-driven model which mathematically quantifies a peer review risk score for each individual exam and uses this data to identify high risk exams and readers, and selectively target these exams for peer review. An analogous model can also be created to assist in the assignment of these peer review cases in keeping with specific priorities of the service provider. An additional option to enhance the peer review process would be to assign the peer review cases in a truly blinded fashion. In addition to eliminating traditional peer review bias, this approach has the potential to better define exam-specific standard of care, particularly when multiple readers participate in the peer review process.

Redefining the Practice of Peer Review Through Intelligent Automation Part 1: Creation of a Standardized Methodology and Referenceable Database.

Conventional peer review practice is compromised by a number of well-documented biases, which in turn limit standard of care analysis, which is fundamental to determination of medical malpractice. In addition to these intrinsic biases, other existing deficiencies exist in current peer review including the lack of standardization, objectivity, retrospective practice, and automation. An alternative model to address these deficiencies would be one which is completely blinded to the peer reviewer, requires independent reporting from both parties, utilizes automated data mining techniques for neutral and objective report analysis, and provides data reconciliation for resolution of finding-specific report differences. If properly implemented, this peer review model could result in creation of a standardized referenceable peer review database which could further assist in customizable education, technology refinement, and implementation of real-time context and user-specific decision support.

Strategies for Medical Data Extraction and Presentation Part 3: Automated Context- and User-Specific Data Extraction.

In current medical practice, data extraction is limited by a number of factors including lack of information system integration, manual workflow, excessive workloads, and lack of standardized databases. The combined limitations result in clinically important data often being overlooked, which can adversely affect clinical outcomes through the introduction of medical error, diminished diagnostic confidence, excessive utilization of medical services, and delays in diagnosis and treatment planning. Current technology development is largely inflexible and static in nature, which adversely affects functionality and usage among the diverse and heterogeneous population of end users. In order to address existing limitations in medical data extraction, alternative technology development strategies need to be considered which incorporate the creation of end user profile groups (to account for occupational differences among end users), customization options (accounting for individual end user needs and preferences), and context specificity of data (taking into account both the task being performed and data subject matter). Creation of the proposed context- and user-specific data extraction and presentation templates offers a number of theoretical benefits including automation and improved workflow, completeness in data search, ability to track and verify data sources, creation of computerized decision support and learning tools, and establishment of data-driven best practice guidelines.

Strategies for medical data extraction and presentation part 2: creating a customizable context and user-specific patient reference database.

One of the greatest challenges facing healthcare professionals is the ability to directly and efficiently access relevant data from the patient's healthcare record at the point of care; specific to both the context of the task being performed and the specific needs and preferences of the individual end-user. In radiology practice, the relative inefficiency of imaging data organization and manual workflow requirements serves as an impediment to historical imaging data review. At the same time, clinical data retrieval is even more problematic due to the quality and quantity of data recorded at the time of order entry, along with the relative lack of information system integration. One approach to address these data deficiencies is to create a multi-disciplinary patient referenceable database which consists of high-priority, actionable data within the cumulative patient healthcare record; in which predefined criteria are used to categorize and classify imaging and clinical data in accordance with anatomy, technology, pathology, and time. The population of this referenceable database can be performed through a combination of manual and automated methods, with an additional step of data verification introduced for data quality control. Once created, these referenceable databases can be filtered at the point of care to provide context and user-specific data specific to the task being performed and individual end-user requirements.

Strategies for medical data extraction and presentation part 1: current limitations and deficiencies.

Data overload is a burgeoning challenge for the medical imaging community; with resulting technical, clinical, and economic ramifications. A primary concern for radiologists is the timely, efficient, and accurate extraction of imaging and clinical data, which collectively are essential in determining accurate diagnosis. In current practice, imaging data retrieval is limited by the fact that imaging and report data are de-coupled from one another, along with the non-standardized and often ambiguous free text data contained within narrative radiology reports. Clinical data retrieval is equally challenging and flawed by the lack of information system integration, paucity of clinical order entry data, and diminished role of the technologist in providing clinical data. These combined factors have the potential to adversely affect radiologist performance and clinical outcomes by diminishing workflow, report accuracy, and diagnostic confidence. New and innovative strategies are required to improve and automate data extraction and presentation, in a context- and user-specific fashion.

The quality/safety medical index: implementation and analysis.

Medical analytics relating to quality and safety measures have become particularly timely and of high importance in contemporary medical practice. In medical imaging, the dynamic relationship between medical imaging quality and radiation safety creates challenges in quantifying quality or safety independently. By creating a standardized measurement which simultaneously accounts for quality and safety measures (i.e., quality safety index), one can in theory create a standardized method for combined quality and safety analysis, which in turn can be analyzed in the context of individual patient, exam, and clinical profiles. The derived index measures can be entered into a centralized database, which in turn can be used for comparative performance of individual and institutional service providers. In addition, data analytics can be used to create customizable educational resources for providers and patients, clinical decision support tools, technology performance analysis, and clinical/economic outcomes research.

Opportunities for radiation-dose optimization through standardized analytics and decision support.

Although the potential for adverse clinical outcomes related to medical radiation have been well documented for over a century, several relatively recent trends have increased awareness of radiation safety in medical imaging. These include expanded CT applications and utilization, increased patient attention on radiation carcinogenesis, and a wide array of legislative and societal radiation initiatives, created partly in response to media reports of CT-induced radiation complications. With this heightened radiation awareness and scrutiny comes a unique and timely opportunity for the collective medical-imaging community to incorporate comparative radiation metrics and analysis directly into routine workflow and reporting. If properly performed, a number of benefits could in theory be derived, including improved clinical outcomes, creation of data-driven best practice guidelines, opportunities for enhanced education and research, dose-reduction technology innovation, and reversal of existing commoditization trends.

Hidden costs of poor image quality: a radiologist's perspective.

Although image quality is a well-recognized component in the successful delivery of medical imaging services, it has arguably declined over the past decade owing to several technical, economic, cultural, and geographic factors. To improve quality, the radiologist community must take a more proactive role in image quality analysis and optimization; these require analysis of not just the single step of image acquisition but the entire imaging chain. Radiologists can benefit through improved report accuracy, diagnostic confidence, and workflow efficiency. The derived data-driven analyses offer an objective means for provider performance analysis, which can help combat commoditization trends and self-referral by nonradiologist providers.

WITHDRAWN: A Crisis in Confidence: A Combined Challenge and Opportunity for Medical Imaging Providers.

The Publisher regrets that this article is an accidental duplication of an article that has already been published, http://dx.doi.org/10.1016/j.jacr.2013.10.022. The duplicate article has therefore been withdrawn.